name: test-write-review-loop
version: 1
description: >
  MiniMax writes tests from skeletons, Sonnet reviews AND judges in one node
  (writes its own verdict file — no separate judge node), loop until clean.
runtime: code-sonnet-tdd-repo
input:
  state: needs-tests
  tags_required: [test-needed]
  required_artifacts: [test_file]
output:
  state: test-write-pending
scope_budget:
  wall_clock_seconds_max: 7200 # must be >= iterations_max * per_iteration_seconds_max
                                # (5 * 1200 = 6000) plus slack
  iterations_max: 5
  per_iteration_seconds_max: 1200
nodes:
  - id: write-minimax
    kind: agent
    role: test-write-review  # M36 v0.6 (bug 69370eda fix): role + model replaces
                             # the ungrounded `template: minimax-test-writer`
                             # (a composite that never existed in the catalog).
    model: minimax-m2
    runtime_env:
      # WF-COMP-15: stage agents share one per-item work branch so their work
      # accumulates across iterations.
      AGENT_REPO_URL: "git@gitea.oreillyit.nz-ai-enablement:skynet/agent-runtimes-agents.git"
      AGENT_BRANCH: "task/${item.uuid}"
  - id: review-sonnet
    kind: agent
    role: test-write-review
    tier: coding
    depends_on: [write-minimax]
    runtime_env:
      AGENT_REPO_URL: "git@gitea.oreillyit.nz-ai-enablement:skynet/agent-runtimes-agents.git"
      AGENT_BRANCH: "task/${item.uuid}"
    prompt: |
      The agent-runtimes project repo is cloned at /workspace/project.
      Change to that directory before doing any work.

      Review the tests just written for the following task.

      **Title**: ${artifacts.item_title}

      Steps:
      1. cd /workspace/project
      2. Review the newly-written test file(s) against the task's spec
         requirements and the test skeleton they were written from:
         - Do the tests actually exercise the required behaviour, not just
           call the code?
         - Are edge cases and failure modes covered?
         - Are assertions specific (not just "no exception raised")?
         - Do the tests pass against the current implementation?
      3. If the tests are inadequate, fix them directly on this branch —
         you are both reviewer and judge for this loop
      4. Write exactly CLEAN or NEEDS_REWORK (nothing else, no trailing
         punctuation or explanation) to /workspace/.workflow/verdict
  - id: review-gate
    kind: script
    cmd: scripts/workflow/verdict-gate
    depends_on: [review-sonnet]
loop:
  body: [write-minimax, review-sonnet, review-gate]
  condition_node: review-gate
  on_max_reached: escalate
escalation:
  loop_max_reached: fix-test-fixture-sonnet